A time-delay neural network model for unconstrained nonconvex optimization
This authors present some convergence and bound results on the trajectory and energy function of general neural network models. A new first-order time-delay neural network model is developed to solve unconstrained nonconvex optimization problems. It can be regarded an useful extension of the Barzilai-Borwein gradient method to neural network models. Their analysis for general neural network implies that the new neural network model is globally convergent to an equilibrium point or stationary point. Simulation results show that the new model is quite efficient. For the entire collection see [Zbl 1402.65005].
- scientific article; zbMATH DE number 2134484
- Stability analysis of gradient-based neural networks for optimization problems
- An optimization neural network model with time-dependent and lossy dynamics
- A one-layer recurrent neural network for constrained nonconvex optimization
- scientific article; zbMATH DE number 1497340
- An optimization neural network model with time-dependent and lossy dynamics
- scientific article; zbMATH DE number 1246232 (Why is no real title available?)
- Stability analysis of gradient-based neural networks for optimization problems
- Gradient-Based Differential Neural-Solution to Time-Dependent Nonlinear Optimization
This page was built for publication: A time-delay neural network model for unconstrained nonconvex optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1627490)
